Systems and methods for privacy-aware weapon anomaly detection via integrated object recognition and skeletal motion analysis

The integration of real-time object detection and skeletal motion analysis with anonymization and late fusion techniques addresses the limitations of conventional systems, enhancing accuracy and reducing false positives in weapon threat detection.

US12462609B1Active Publication Date: 2025-11-04FLORIDA INTERNATIONAL UNIVERSITY
View PDF 3 Cites 2 Cited by

Patent Information

Application Number
US19/271242
Authority / Receiving Office
US · United States
Patent Type
Patents(United States)
Current Assignee / Owner
Filing Date
2025-07-16
Publication Date
2025-11-04
Estimated Expiration
2045-07-16

AI Technical Summary

Technical Problem

Conventional video anomaly detection systems struggle with false positives and lack contextual awareness in dynamic environments, particularly in identifying weapon-related threats due to the variability of human motion and the absence of object detection capabilities.

Method used

Integrates real-time object detection with skeletal motion analysis, employing a fine-tuned model to detect weapons and humans, anonymizes unarmed individuals, and applies a late fusion technique to refine anomaly scores, optimizing computational efficiency and accuracy.

Benefits of technology

Enhances threat discrimination by reducing false positives and improving accuracy in anomaly detection while preserving privacy, ensuring reliable and context-aware surveillance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US12462609-D00000_ABST
    Figure US12462609-D00000_ABST
Patent Text Reader

Abstract

Systems, methods, and frameworks are provided for privacy-aware weapon anomaly detection via integrated object recognition and skeletal motion analysis. This framework integrates real-time object detection and motion analysis to identify weapon anomalies in video surveillance while preserving privacy. The framework combines a fine-tuned object detection model, a head-segmentation module for anonymizing unarmed individuals, and a skeleton-based motion analysis module to detect threatening behaviors. By refining and fusing detection and motion analysis outputs, the framework enhances detection accuracy and reduces false positives, thereby providing a reliable solution for intelligent, privacy-preserving surveillance applications.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Using artificial intelligence to analyze output from a security system to detect a potential crime in progress

    US11335126B1

  • Privacy-based monitoring system and method

    US20240354446A1

  • System and method for weapon detection with pose estimation

    US20250182450A1

Cited By

  • Sludge filter pressing system based on automatic operation

    CN121517085A

  • Method and system for calibration of detection thresholds in video object detection

    US20250259410A1